An agricultural optimization method and system fusing agricultural producer behavior simulation

Abstract

This invention discloses an agricultural optimization method and system that integrates simulation of agricultural producer behavior. The method includes: integrating and unifying the scale of multi-source data to obtain a standardized database; simulating agricultural producer behavior to output aggregated data at the farmer scale; constructing a multi-sectoral equilibrium model; using the data in the standardized database as a basis, combined with the aggregated data at the farmer scale, to output regional equilibrium results; establishing a dual-scale linkage control mechanism between the region and farmers; constructing and solving a multi-objective optimization model, with farmer income increase, water conservation, emission reduction, and stable grain production as objective functions, and using an optimization algorithm to solve the multi-objective optimization model to output a configuration scheme adapted to production practice. Its beneficial effects are: this invention solves the problems of traditional schemes ignoring farmer heterogeneity, insufficient multi-factor coupling, and lack of coordinated adaptation between macro-regions and micro-farmers; and it can obtain an implementable optimal layout scheme at the plot scale.

Description

Technical Field

[0001] This invention relates to the field of agricultural resource management technology, specifically to an agricultural optimization method and system that integrates simulation of agricultural producer behavior. Background Technology

[0002] Current research on agricultural layout optimization and resource allocation mainly employs statistical regression models, single-objective optimization models, regional equilibrium models, or sectoral equilibrium models. However, statistical regression models struggle to characterize the behavioral heterogeneity caused by individual differences among farmers, single-objective optimization models cannot simultaneously address diverse demands such as water conservation, stable grain production, low carbon emissions, and increased income, regional equilibrium models lack accurate simulation of micro-level production behaviors, and sectoral equilibrium models cannot achieve spatial implementation at the plot scale.

[0003] The aforementioned traditional schemes generally fail to express the heterogeneous behavior of farmers, lack multi-factor coupling, and lack the synergistic adaptation between macro-regions and micro-farmers, thus making it difficult to obtain an optimal layout scheme at the plot scale that can be implemented. Summary of the Invention

[0004] In view of the technical defects mentioned in the background art, the purpose of the embodiments of the present invention is to provide an agricultural optimization method and system that integrates agricultural producer behavior simulation, aiming to at least solve one of the technical problems in the related art to a certain extent.

[0005] To achieve the above objectives, in a first aspect, embodiments of the present invention provide an agricultural optimization method that integrates simulation of agricultural producer behavior, the method comprising the following steps:

[0006] Multi-source data integration and scale unification: Based on the collected remote sensing plots, farmer surveys, climate, cost-benefit, agricultural carbon emissions and regional input-output tables, the data are processed and unified into a three-level scale system that includes regions, plots and farmers, so as to obtain a standardized database.

[0007] The behavior of agricultural producers is simulated. Based on a pre-constructed simulation model of agricultural producer behavior, and combined with the heterogeneity attributes of farmers and the utility maximization decision rules in the standardized database, the micro-behavior of agricultural producers is simulated to output aggregated data at the farmer scale. The simulation includes farmers' adjustments to planting structure, input choices, responses to price changes and subsidy policies, and responses to climate risks.

[0008] A multi-sector equilibrium model is constructed. Using the constructed resource equilibrium, carbon emission equilibrium, and economic equilibrium equations, water resource constraints, soil carrying capacity, carbon emission and carbon reduction costs, and economic benefits and input-output tables are coupled. Based on data from the standardized database and combined with the aggregated data at the farmer scale, regional equilibrium results are output. These regional equilibrium results provide decision boundaries for simulating agricultural producer behavior.

[0009] Establish a dual-scale linkage control mechanism between regions and farmers; through a cyclical mechanism of transmitting regional constraints to the simulation model, uploading farmer behavior from the simulation model, updating equilibrium results, and iteratively adjusting constraints, to achieve coordinated adaptation between macro-regions and micro-farmers;

[0010] The construction and solution of a multi-objective optimization model: taking farmers' income increase, water conservation, emission reduction and stable grain production as objective functions, combining regional constraints and farmers' management capacity constraints, and using optimization algorithms to solve the multi-objective optimization model, outputting a configuration scheme that is adapted to production practice.

[0011] As one specific implementation of this application, the heterogeneous attributes of farmers include operating scale, risk preference, financial capacity, labor force size, and technology adoption rate;

[0012] The utility maximization decision rules include planting structure adjustment triggering conditions, input selection rules, policy response rules, and climate risk response rules.

[0013] As a specific implementation of this application, the combination of farmer heterogeneity attributes and utility maximization decision rules in the standardized database specifically includes:

[0014] Each farmer is assigned a unique combination of heterogeneous parameters to obtain the corresponding attribute label;

[0015] Individualized trigger judgments for decision rules are used to obtain the corresponding trigger rules;

[0016] Based on the triggering rules and attribute tags, a set of candidate solutions is generated;

[0017] The utility value of each candidate solution is calculated, and the candidate solution with the highest utility value is selected as the farmer's final decision, providing micro-input for the multi-sector equilibrium model.

[0018] As a specific implementation of this application, the establishment of a dual-scale linkage regulation mechanism between regions and farmers specifically includes:

[0019] The initial calculated regional equilibrium result is passed to the simulation model as a constraint; wherein, the regional equilibrium result includes the crop selection set, water resource ceiling, carbon emission limit, and price range;

[0020] The simulation model simulates farmers' decisions based on the constraints, outputs farmer-scale results, and summarizes them into regional-level data.

[0021] The multi-sector equilibrium model substitutes the aggregated data into each equilibrium equation to verify whether the conditions for resource, carbon emission, and economic equilibrium are met.

[0022] If any equilibrium deviation is greater than the threshold, the constraint conditions are updated and transmitted back to the simulation model; if the deviation is less than the threshold, the iteration stops.

[0023] As a preferred implementation of this application, the output configuration scheme adapted to production practice specifically includes: outputting a plot-scale planting layout map, a regional resource allocation scheme, a distribution of farmers' response behaviors, and an impact analysis of different policy scenarios, in order to adapt to different agricultural regions and policy needs.

[0024] As a specific implementation of this application, the results of the policy scenario include a comparison table of the impacts of different policy combinations and a classification diagram of farmer response patterns; wherein, the policy combination is any combination of subsidies, carbon prices, water restrictions and quota policies;

[0025] The impact analysis of scenarios involves setting a baseline scenario, a policy intervention scenario, and a climate scenario, and then substituting them into the optimization solution to output the optimization results and difference analysis under each scenario, adapting to different regions and policy needs.

[0026] Secondly, embodiments of the present invention also provide an agricultural optimization system that integrates simulation of agricultural producer behavior, comprising:

[0027] The data acquisition module is used for multi-source data integration and scale unification. Based on the collected remote sensing plots, farmer surveys, climate, cost-benefit, agricultural carbon emissions and regional input-output tables, the data are processed and unified into a three-level scale system that includes regions, plots and farmers, so as to obtain the constructed standardized database.

[0028] The behavioral simulation module is used to simulate the behavior of agricultural producers. Based on a pre-built agricultural producer behavior simulation model, combined with the heterogeneous attributes of farmers and utility maximization decision rules in the standardized database, the micro-behavior of agricultural producers is simulated to output aggregated data at the farmer scale. The simulation includes farmers' adjustments to planting structure, input choices, responses to price changes and subsidy policies, and responses to climate risks.

[0029] The sectoral equilibrium model module is used to construct multi-sectoral equilibrium models. It utilizes the constructed resource equilibrium, carbon emission equilibrium, and economic equilibrium equations, coupled with water resource constraints, soil carrying capacity, carbon emission and carbon reduction costs, and economic benefits and input-output tables. Based on the data in the standardized database, it combines the aggregated data at the farmer scale to output regional equilibrium results. The regional equilibrium results provide decision boundaries for simulating the behavior of agricultural producers.

[0030] The dual-scale control module is used to establish a dual-scale linkage control mechanism between regions and farmers. Through a cyclical mechanism of transmitting regional constraints to the simulation model, uploading farmer behavior from the simulation model, updating equilibrium results, and iteratively adjusting constraints, it achieves coordinated adaptation between macro-regions and micro-farmers.

[0031] The multi-objective optimization module is used to construct and solve multi-objective optimization models. It takes increasing farmers' income, saving water, reducing emissions, and stabilizing grain production as objective functions, combines regional constraints and farmers' management capacity constraints, and uses optimization algorithms to solve the multi-objective optimization model, outputting a configuration scheme that is adapted to production practice.

[0032] Thirdly, embodiments of the present invention also provide an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement an agricultural optimization method integrating agricultural producer behavior simulation as described in the first aspect.

[0033] The beneficial effects of this invention are as follows: This invention first collects multi-source heterogeneous data and unifies the scale to construct a simulation model of agricultural producer behavior that includes the heterogeneous attributes of farmers. Then, it constructs a multi-sectoral equilibrium model that couples water resource constraints, soil carrying capacity, and carbon emissions. Through a dual-scale linkage control mechanism of regional constraint downlink and farmer behavior uplink, the two are cyclically iteratively converged. This leads to the construction of a multi-objective optimization model with water conservation, emission reduction, increased farmer income, and stable grain production as the core objectives. An intelligent evolutionary algorithm is used to solve for the optimal solution, and finally, a configuration scheme adapted to production practice is output. This solves the problems of traditional schemes ignoring farmer heterogeneity, insufficient multi-factor coupling, and lack of coordination and adaptation between macro-regions and micro-farmers. As a result, it can obtain an implementable optimal layout scheme at the plot scale, providing an innovative decision-making tool for agricultural structure optimization, increased farmer income, and agricultural carbon emission reduction. Attached Figure Description

[0034] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings used in the description of the specific embodiments or the prior art will be briefly introduced below.

[0035] Figure 1This is a flowchart of an agricultural optimization method that integrates simulation of agricultural producer behavior, provided in an embodiment of the present invention.

[0036] Figure 2 This is a principle block diagram of an agricultural optimization system that integrates agricultural producer behavior simulation provided in an embodiment of the present invention;

[0037] Figure 3 This is a structural diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0038] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0039] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0040] ABM: Agent-Based Modeling, is a computational simulation method used to simulate the decision-making behavior and interactions of agricultural producers, thereby revealing the macro-dynamics of agricultural systems. It is particularly adept at handling the heterogeneity, complexity, and self-organizing characteristics that are prevalent in agricultural systems.

[0041] It should be noted that, unless otherwise stated, the technical terms used in this embodiment have the common meaning as understood in the relevant technical field.

[0042] Please refer to Figure 1 The present invention provides an agricultural optimization method that integrates simulation of agricultural producer behavior, the method comprising the following steps:

[0043] S101, Multi-source data integration and scale unification: Based on the collected remote sensing plots, farmer surveys, climate, cost-benefit, agricultural carbon emissions and regional input-output tables, the data are processed and unified into a three-level scale system including regions, plots and farmers, so as to obtain the constructed standardized database.

[0044] S102, Simulate agricultural producer behavior; Based on a pre-built simulation model of agricultural producer behavior, combined with the heterogeneous attributes of farmers and utility maximization decision rules in the standardized database, simulate the micro-behavior of agricultural producers to output summary data at the farmer scale; The simulation includes farmers' adjustments to planting structure, input choices, responses to price changes and subsidy policies, and responses to climate risks.

[0045] S103, Construction of a multi-sector equilibrium model; using the constructed resource equilibrium, carbon emission equilibrium, and economic equilibrium equations, coupled with water resource constraints, soil carrying capacity, carbon emission and carbon reduction costs, and economic benefits and input-output tables, and based on the data in the standardized database, combined with the aggregated data at the farmer scale, to output regional equilibrium results; wherein, the regional equilibrium results provide decision boundaries for simulating the behavior of agricultural producers;

[0046] S104. Establish a dual-scale linkage control mechanism between regions and farmers; through a cyclical mechanism of transmitting regional constraints to the simulation model, uploading farmer behavior from the simulation model, updating equilibrium results, and iteratively adjusting constraints, to achieve coordinated adaptation between macro-regions and micro-farmers.

[0047] S105, Construction and solution of multi-objective optimization model: Taking farmers' income increase, water conservation, emission reduction and stable grain production as objective functions, combined with regional constraints and farmers' management capacity constraints, and using optimization algorithms to solve the multi-objective optimization model, outputting a configuration scheme that is adapted to production practice.

[0048] In step S101, the remote sensing plot data collected from multiple sources includes plot boundaries, slope, and current planting status; farmer survey data includes operating scale, risk preference, funding amount, labor force, and technology adoption; climate data includes average daily temperature, precipitation, and frequency of extreme weather in recent years; cost-benefit data includes input costs such as seeds, fertilizers, pesticides, machinery, and labor, as well as crop selling prices; agricultural carbon emission data includes carbon emission coefficients per unit area for different crops and carbon reduction costs; regional input-output tables include correlation data between the agricultural sector and industry and service sectors; and resource data includes available water resources, soil fertility level, and soil suitability evaluation results.

[0049] Processing procedure: Geographic registration, data standardization, and interpolation completion methods are used to unify farmer-scale, plot-scale, and regional-scale data into a three-level scale system of region-plot-farmer, constructing a standardized database to ensure spatiotemporal consistency of data; the standardized dataset includes a farmer heterogeneity parameter library, a plot attribute library, and a regional resource-economic-environment parameter library, etc.

[0050] In step S102, the step of combining the heterogeneity attributes of farmers in the standardized database with the utility maximization decision rule specifically includes:

[0051] Each farmer is assigned a unique combination of heterogeneous parameters to obtain the corresponding attribute label;

[0052] Individualized trigger judgments for decision rules are used to obtain the corresponding trigger rules;

[0053] Based on the triggering rules and attribute tags, a set of candidate solutions is generated;

[0054] The utility value of each candidate solution is calculated, and the candidate solution with the highest utility value is selected as the farmer's final decision, providing micro-input for the multi-sector equilibrium model.

[0055] In this embodiment, the heterogeneity attributes of farmers include operating scale, risk preference, financial capacity, labor force size, and technology adoption rate;

[0056] Operating scale: quantified by the total planting area of ​​the plot;

[0057] Risk preference: quantified by a risk aversion coefficient and calibrated through risk selection questions in a farmer questionnaire;

[0058] Financial capacity: quantified by the amount of disposable production funds and financing coefficient;

[0059] Labor force size: quantified by the number of family agricultural laborers and labor productivity (mu / person);

[0060] Technology adoption rate: quantified by the proportion of water-saving and low-carbon technologies applied.

[0061] The utility maximization decision rules include planting structure adjustment triggering conditions, input selection rules, policy response rules, and climate risk response rules.

[0062] Based on the utility maximization theory, a farmer decision function is constructed: utility = income × risk preference coefficient - input cost × capital constraint coefficient - climate risk loss × risk tolerance threshold, thereby simulating the dynamic decision-making process of farmers.

[0063] Planting structure adjustment: When crop price fluctuations exceed 5% or policy subsidies change by more than 10%, planting ratio adjustments are triggered;

[0064] Investment selection rules: When the capital constraint coefficient is >0.8, prioritize low-cost investment combinations; when the technology adoption rate is >0.6, prioritize low-carbon and water-saving investments.

[0065] Policy response: Response strength to subsidy policy = subsidy amount × price sensitivity coefficient; Response strength to carbon price policy = carbon price × carbon emission intensity coefficient.

[0066] Climate risk response rules: When the frequency of extreme weather events exceeds 20% of the average of recent years, adjust the planting ratio of drought-resistant / flood-resistant crops.

[0067] In step S103, the resource balance equation is: water supply = total water consumption of all crops, and soil carrying capacity threshold = planting area of ​​each crop × soil demand per unit area.

[0068] Carbon emission balance equation: Total regional carbon emissions = Sum of carbon emissions from all crops ≤ Regional carbon emission quota;

[0069] Economic equilibrium equation: Total revenue of the agricultural sector = crop yield × selling price - total input cost, and the input and output of the agricultural sector are balanced with those of other sectors, based on the regional input and output table.

[0070] Water resource constraint parameters: calculated based on the available water resources and irrigation efficiency in the region, including the water consumption quota per unit area of ​​crops and the upper limit of total water consumption in the region;

[0071] Soil constraint parameters: Based on soil fertility level and suitability evaluation results, determine the suitable planting area and yield limit for different crops;

[0072] Carbon emission parameters: Referring to the IPCC methodology and combining local measured data, carbon emission coefficients per unit area and carbon reduction cost curves for different crops are constructed; among them, the IPCC carbon emission coefficient refers to the emission factor defined by the Intergovernmental Panel on Climate Change (IPCC) in the Greenhouse Gas Inventory Guidelines;

[0073] Economic parameters: Based on farmer survey cost-benefit data and regional statistical data, an agricultural sector input-output matrix and crop price elasticity coefficient are constructed. This achieves multi-factor coupling of related regional water, soil, carbon, and economy.

[0074] In step S104, the establishment of a dual-scale linkage regulation mechanism between the region and farmers specifically includes:

[0075] The initial calculated regional equilibrium result is passed to the simulation model as a constraint; wherein, the regional equilibrium result includes the crop selection set, water resource ceiling, carbon emission limit, and price range;

[0076] The simulation model simulates farmers' decisions based on the constraints, outputs farmer-scale results, and summarizes them into regional-level data.

[0077] The multi-sector equilibrium model substitutes the aggregated data into each equilibrium equation to verify whether the conditions for resource, carbon emission, and economic equilibrium are met.

[0078] If any equilibrium deviation is greater than the threshold, the constraint conditions are updated and transmitted back to the simulation model; if the deviation is less than the threshold, the iteration stops.

[0079] This allows the rationality of determining the regional equilibrium outcome through aggregated data on farmers' behavior. The equilibrium constraints of the multi-sector equilibrium model directly define the decision boundary of the simulation model of agricultural producer behavior, and the two form a two-way calibration between micro-behavior and macro-equilibrium.

[0080] Finally, the regional constraint parameters and the summary data of farmers' behavior output in step S104 are directly used as the feasible solution space for multi-objective optimization in step S105, ensuring that the optimization results do not deviate from reality. Through the feasible solution space after convergence of dual-scale linkage, invalid solutions that deviate from actual constraints are eliminated, providing high-quality input for the multi-objective optimization model and improving optimization efficiency and feasibility of results.

[0081] In step S105, use NSGA-II, MOEA / D, or an improved PSO to solve;

[0082] The configuration scheme that adapts the output to production practice specifically includes:

[0083] Output plot-scale planting layout maps, regional resource allocation plans, distribution of farmer response behaviors, and impact analysis of different policy scenarios to adapt to different agricultural regions and policy needs.

[0084] In this embodiment, the results of the policy scenario include a comparison table of the impacts of different policy combinations and a classification diagram of farmer response patterns; wherein, the policy combination is any combination of subsidies, carbon prices, water restrictions, and quota policies;

[0085] The impact analysis of scenarios involves setting a baseline scenario, a policy intervention scenario, and a climate scenario, and then substituting them into the aforementioned model for optimization. The results of optimization under each scenario and the analysis of differences are output to adapt to different regions and policy needs.

[0086] The above-mentioned scheme first collects heterogeneous data from multiple sources and unifies the scale to construct a simulation model of agricultural producer behavior that includes the heterogeneous attributes of farmers. Then, it constructs a multi-sectoral equilibrium model that couples water resource constraints, soil carrying capacity, and carbon emissions. Through a dual-scale linkage control mechanism of regional constraint downlink and farmer behavior uplink, it achieves iterative convergence of the two, and then constructs a multi-objective optimization model with water conservation, emission reduction, increased farmer income, and stable grain production as its core. It uses an intelligent evolutionary algorithm to solve for the optimal solution, and finally outputs a configuration scheme that is adapted to production practice. This solves the problems of traditional schemes ignoring farmer heterogeneity, insufficient multi-factor coupling, and lack of coordinated adaptation between macro-regions and micro-farmers. As a result, it can obtain an implementable optimal layout scheme at the plot scale, which can provide an innovative decision-making tool for agricultural structure optimization, increased farmer income, and agricultural carbon emission reduction.

[0087] Based on the same inventive concept, embodiments of the present invention also provide an agricultural optimization system that integrates simulation of agricultural producer behavior, referring to... Figure 2 ,include:

[0088] The data acquisition module is used for multi-source data integration and scale unification. Based on the collected remote sensing plots, farmer surveys, climate, cost-benefit, agricultural carbon emissions and regional input-output tables, the data are processed and unified into a three-level scale system that includes regions, plots and farmers, so as to obtain the constructed standardized database.

[0089] The behavioral simulation module is used to simulate the behavior of agricultural producers. Based on a pre-built agricultural producer behavior simulation model, combined with the heterogeneous attributes of farmers and utility maximization decision rules in the standardized database, the micro-behavior of agricultural producers is simulated to output aggregated data at the farmer scale. The simulation includes farmers' adjustments to planting structure, input choices, responses to price changes and subsidy policies, and responses to climate risks.

[0090] The sectoral equilibrium model module is used to construct multi-sectoral equilibrium models. It utilizes the constructed resource equilibrium, carbon emission equilibrium, and economic equilibrium equations, coupled with water resource constraints, soil carrying capacity, carbon emission and carbon reduction costs, and economic benefits and input-output tables. Based on the data in the standardized database, it combines the aggregated data at the farmer scale to output regional equilibrium results. The regional equilibrium results provide decision boundaries for simulating the behavior of agricultural producers.

[0091] The dual-scale control module is used to establish a dual-scale linkage control mechanism between regions and farmers. Through a cyclical mechanism of transmitting regional constraints to the simulation model, uploading farmer behavior from the simulation model, updating equilibrium results, and iteratively adjusting constraints, it achieves coordinated adaptation between macro-regions and micro-farmers.

[0092] The multi-objective optimization module is used to construct and solve multi-objective optimization models. It takes increasing farmers' income, saving water, reducing emissions, and stabilizing grain production as objective functions, combines regional constraints and farmers' management capacity constraints, and uses optimization algorithms to solve the multi-objective optimization model, outputting a configuration scheme that is adapted to production practice.

[0093] Furthermore, the heterogeneous attributes of farmers include operating scale, risk appetite, financial capacity, labor force size, and technology adoption rate;

[0094] The utility maximization decision-making rules include planting structure adjustment triggering conditions, input selection rules, policy response, and climate risk response rules;

[0095] The combination of farmer heterogeneity attributes and utility maximization decision rules in the standardized database specifically includes:

[0096] Each farmer is assigned a unique combination of heterogeneous parameters to obtain the corresponding attribute label;

[0097] Individualized trigger judgments for decision rules are used to obtain the corresponding trigger rules;

[0098] Based on the triggering rules and attribute tags, a set of candidate solutions is generated;

[0099] The utility value of each candidate solution is calculated, and the candidate solution with the highest utility value is selected as the farmer's final decision, providing micro-input for the multi-sector equilibrium model.

[0100] It should be noted that the core positioning of the multi-sector equilibrium model is to couple four-dimensional factors of water, soil, carbon, and economy to provide decision boundaries for ABM and to verify the regional adaptability of aggregated farmer behavior data; specifically, it includes the following core hierarchical architecture:

[0101] 1. Constraint Layer: Clearly define the hard constraint boundaries of the region, including available water resources, soil carrying capacity thresholds, carbon emission quotas, and total crop planting control targets;

[0102] 2. Equilibrium Equation Layer: The kernel achieves multi-factor coupling through the constructed equilibrium equations, ensuring regional balance of resource supply and demand, carbon emissions, and economic balance.

[0103] 3. Parameter Support Layer: A regional resource-economic-environment parameter library based on standardized datasets, providing key parameters such as water resource quotas, carbon emission coefficients, and input-output ratios.

[0104] In this embodiment, the establishment of a dual-scale linkage control mechanism between regions and farmers specifically includes:

[0105] The initial calculated regional equilibrium result is passed to the simulation model as a constraint; wherein, the regional equilibrium result includes the crop selection set, water resource ceiling, carbon emission limit, and price range;

[0106] The simulation model simulates farmers' decisions based on the constraints, outputs farmer-scale results, and summarizes them into regional-level data.

[0107] The multi-sector equilibrium model substitutes the aggregated data into each equilibrium equation to verify whether the conditions for resource, carbon emission, and economic equilibrium are met.

[0108] If any equilibrium deviation is greater than the threshold, the constraint conditions are updated and transmitted back to the simulation model; if the deviation is less than the threshold, the iteration stops.

[0109] It should be noted that for more specific details of the system implementation and the description of the working process, please refer to the aforementioned method implementation section, which will not be repeated here.

[0110] By first collecting heterogeneous data from multiple sources and unifying the scale, a simulation model of agricultural producer behavior incorporating the heterogeneous attributes of farmers is constructed. Then, a multi-sectoral equilibrium model coupling water resource constraints, soil carrying capacity, and carbon emissions is built. Through a dual-scale linkage control mechanism of regional constraint downlink and farmer behavior uplink, the two models achieve iterative convergence. This leads to the construction of a multi-objective optimization model centered on water conservation, emission reduction, increased farmer income, and stable grain production. An intelligent evolutionary algorithm is used to solve for the optimal solution, ultimately outputting a configuration scheme adapted to production practices. This addresses the problems of traditional schemes neglecting farmer heterogeneity, insufficient multi-factor coupling, and lack of coordinated adaptation between macro-regional and micro-farmer levels. Consequently, an implementable optimal layout scheme at the plot scale can be obtained, providing an innovative decision-making tool for agricultural structure optimization, increased farmer income, and agricultural carbon emission reduction.

[0111] In another embodiment of the present invention, an electronic device is also provided, with reference to... Figure 3 As shown, it includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the program to implement an agricultural optimization method that integrates simulation of agricultural producer behavior as described in the preceding embodiments.

[0112] It should be noted that if the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0113] In the several embodiments provided in this application, it should be understood that the described systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0114] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The scope of the preferred embodiments of this application includes other implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order according to the functions involved, as should be understood by those skilled in the art to which the embodiments of this application pertain.

[0115] The integrated modules described above can be implemented in hardware or as software functional modules. When using any module, the collection and storage of user information shall only be carried out with the user's full authorization and in compliance with relevant laws and regulations, protecting the security and privacy of user data, and strictly prohibiting unauthorized access.

[0116] Data processing will be conducted within the scope of the law and will not exceed the purposes and scope authorized by the user; at the same time, users have the right to access, correct, delete, restrict processing, and refuse processing of their personal data; and strictly comply with applicable laws and regulations and conduct compliance reviews.

[0117] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the claims and specification of the present invention.

Claims

1. An agricultural optimization method integrating simulation of agricultural producer behavior, characterized in that, The method includes the following steps: Multi-source data integration and scale unification: Based on the collected remote sensing plots, farmer surveys, climate, cost-benefit, agricultural carbon emissions and regional input-output tables, the data are processed and unified into a three-level scale system that includes regions, plots and farmers, so as to obtain a standardized database. The behavior of agricultural producers is simulated. Based on a pre-constructed simulation model of agricultural producer behavior, and combined with the heterogeneity attributes of farmers and the utility maximization decision rules in the standardized database, the micro-behavior of agricultural producers is simulated to output aggregated data at the farmer scale. The simulation includes farmers' adjustments to planting structure, input choices, responses to price changes and subsidy policies, and responses to climate risks. A multi-sector equilibrium model is constructed. Using the constructed resource equilibrium, carbon emission equilibrium, and economic equilibrium equations, water resource constraints, soil carrying capacity, carbon emission and carbon reduction costs, and economic benefits and input-output tables are coupled. Based on data from the standardized database and combined with the aggregated data at the farmer scale, regional equilibrium results are output. These regional equilibrium results provide decision boundaries for simulating agricultural producer behavior. Establish a dual-scale linkage control mechanism between regions and farmers; through a cyclical mechanism of transmitting regional constraints to the simulation model, uploading farmer behavior from the simulation model, updating equilibrium results, and iteratively adjusting constraints, to achieve coordinated adaptation between macro-regions and micro-farmers; The construction and solution of a multi-objective optimization model: taking farmers' income increase, water conservation, emission reduction and stable grain production as objective functions, combining regional constraints and farmers' management capacity constraints, and using optimization algorithms to solve the multi-objective optimization model, outputting a configuration scheme that is adapted to production practice.

2. The method as described in claim 1, characterized in that, The heterogeneous attributes of farmers include operating scale, risk appetite, financial capacity, labor force size, and technology adoption rate; The utility maximization decision rules include planting structure adjustment triggering conditions, input selection rules, policy response rules, and climate risk response rules.

3. The method as described in claim 2, characterized in that, The combination of farmer heterogeneity attributes and utility maximization decision rules in the standardized database specifically includes: Each farmer is assigned a unique combination of heterogeneous parameters to obtain the corresponding attribute label; Individualized trigger judgments for decision rules are used to obtain the corresponding trigger rules; Based on the triggering rules and attribute tags, a set of candidate solutions is generated; The utility value of each candidate solution is calculated, and the candidate solution with the highest utility value is selected as the farmer's final decision, providing micro-input for the multi-sector equilibrium model.

4. The method as described in claim 2, characterized in that, The establishment of a dual-scale linkage regulation mechanism between regions and farmers specifically includes: The initial calculated regional equilibrium result is passed to the simulation model as a constraint; wherein, the regional equilibrium result includes the crop selection set, water resource ceiling, carbon emission limit, and price range; The simulation model simulates farmers' decisions based on the constraints, outputs farmer-scale results, and summarizes them into regional-level data. The multi-sector equilibrium model substitutes the aggregated data into each equilibrium equation to verify whether the conditions for resource, carbon emission, and economic equilibrium are met. If any equilibrium deviation is greater than the threshold, the constraint conditions are updated and transmitted back to the simulation model; if the deviation is less than the threshold, the iteration stops.

5. The method as described in claim 2, characterized in that, The output configuration scheme adapted to production practice specifically includes: outputting a plot-scale planting layout map, a regional resource allocation scheme, a distribution of farmers' response behaviors, and an impact analysis of different policy scenarios, in order to adapt to different agricultural regions and policy needs.

6. The method as described in claim 5, characterized in that, The results of the policy scenarios include a comparison table of the impacts of different policy combinations and a classification diagram of farmer response patterns; where the policy combinations are any combination of subsidies, carbon prices, water restrictions, and quota policies; The impact analysis of scenarios involves setting a baseline scenario, a policy intervention scenario, and a climate scenario, and then substituting them into the optimization solution to output the optimization results and difference analysis under each scenario, adapting to different regions and policy needs.

7. An agricultural optimization system integrating simulation of agricultural producer behavior, characterized in that, include: The acquisition module is used for multi-source data integration and scale unification; Based on the collected remote sensing data, farmer surveys, climate, cost-benefit, agricultural carbon emissions, and regional input-output tables, the data are processed and unified into a three-level scale system that includes regions, plots, and farmers to obtain a standardized database. The behavioral simulation module is used to simulate the behavior of agricultural producers. Based on a pre-built agricultural producer behavior simulation model, combined with the heterogeneous attributes of farmers and utility maximization decision rules in the standardized database, the micro-behavior of agricultural producers is simulated to output aggregated data at the farmer scale. The simulation includes farmers' adjustments to planting structure, input choices, responses to price changes and subsidy policies, and responses to climate risks. The sector equilibrium model module is used for constructing multi-sector equilibrium models; By utilizing the constructed resource equilibrium, carbon emission equilibrium, and economic equilibrium equations, coupled with water resource constraints, soil carrying capacity, carbon emission and carbon reduction costs, and economic benefits and input-output tables, and based on the data in the standardized database, combined with the aggregated data at the farmer scale, regional equilibrium results are output; wherein, the regional equilibrium results provide decision boundaries for simulating the behavior of agricultural producers. The dual-scale control module is used to establish a dual-scale linkage control mechanism between regions and farmers. Through a cyclical mechanism of transmitting regional constraints to the simulation model, uploading farmer behavior from the simulation model, updating equilibrium results, and iteratively adjusting constraints, it achieves coordinated adaptation between macro-regions and micro-farmers. The multi-objective optimization module is used to construct and solve multi-objective optimization models. It takes increasing farmers' income, saving water, reducing emissions, and stabilizing grain production as objective functions, combines regional constraints and farmers' management capacity constraints, and uses optimization algorithms to solve the multi-objective optimization model, outputting a configuration scheme that is adapted to production practice.

8. The system as described in claim 7, characterized in that, The heterogeneous attributes of farmers include operating scale, risk appetite, financial capacity, labor force size, and technology adoption rate; The utility maximization decision-making rules include planting structure adjustment triggering conditions, input selection rules, policy response, and climate risk response rules; The combination of farmer heterogeneity attributes and utility maximization decision rules in the standardized database specifically includes: Each farmer is assigned a unique combination of heterogeneous parameters to obtain the corresponding attribute label; Individualized trigger judgments for decision rules are used to obtain the corresponding trigger rules; Based on the triggering rules and attribute tags, a set of candidate solutions is generated; The utility value of each candidate solution is calculated, and the candidate solution with the highest utility value is selected as the farmer's final decision, providing micro-input for the multi-sector equilibrium model.

9. The system as described in claim 8, characterized in that, The establishment of a dual-scale linkage regulation mechanism between regions and farmers specifically includes: The initial calculated regional equilibrium result is passed to the simulation model as a constraint; wherein, the regional equilibrium result includes the crop selection set, water resource ceiling, carbon emission limit, and price range; The simulation model simulates farmers' decisions based on the constraints, outputs farmer-scale results, and summarizes them into regional-level data. The multi-sector equilibrium model substitutes the aggregated data into each equilibrium equation to verify whether the conditions for resource, carbon emission, and economic equilibrium are met. If any equilibrium deviation is greater than the threshold, the constraint conditions are updated and transmitted back to the simulation model; if the deviation is less than the threshold, the iteration stops.

10. An electronic device, characterized in that, include: The device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement an agricultural optimization method that integrates simulation of agricultural producer behavior as described in any one of claims 1-6.

Images